SciUniverse - Biology: leaderboard

Biology domain of C5R's SciUniverse Level 1 (2026-09-24): five task families weighted equally. DNA amplification and recovery and cell-free sfGFP expression run physically at the Facility-0 lab; LC-MRM peak review and two simulated Hamilton STARlet liquid-handling workflows (sfGFP PCR; normalization and pooling) run virtually. Pass@1 (%), higher is better.

Metric: Pass@1 (%). Source: c5r.net. Saturation forecast: Around January 2028. 6 models tracked.

Top models

#ModelScoreOverall rank
1GPT-6 Astra (xHigh)60#6 (GPT-6 Astra)
2Claude Fable 5.1 (xHigh)40#14 (Claude Fable 5.1)
3Grok 4.6 (xHigh)32#44 (Grok 4.6)
4Claude Opus 5 (xHigh)31.1#20 (Claude Opus 5)
5Gemini 3.8 Flash (High)28.9#36 (Gemini 3.8 Flash)
6GPT-5.6 Sol (xHigh)15.6#29 (GPT-5.6 Sol)

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=sciuniverse-biology · How It Works · Data refreshed daily, snapshot 2026-11-12.